Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words ending in tense-related markers in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    multilingual code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.65
     Theſe
    -0.63
     createSlice
    -0.59
     становника
    -0.59
    offsetof
    -0.57
     betweenstory
    -0.57
    <bos>
    -0.56
    izade
    -0.55
     //$
    -0.55
    interopRequire
    -0.55
    POSITIVE LOGITS
    czas
    0.56
     ureter
    0.55
    VSS
    0.55
    tettu
    0.52
     milo
    0.50
     amateurs
    0.50
     Ptole
    0.49
     haters
    0.49
     brooklyn
    0.49
     Falkland
    0.49
    Act Density 0.136%

    No Known Activations